Popular repositories Loading

1. DeepSeek-v4-DSpark-Aidendle94-GB10-ServingStack DeepSeek-v4-DSpark-Aidendle94-GB10-ServingStack Public

   Docker compose serving stack for DeepSeek v4 Flash DSpark for NVIDIA Spark GB10 system using Aidendle94 image

   Python 33 3

2. glm-5.3-flash-nvidia-nvfp4-dflash-2x-dgx-sparks glm-5.3-flash-nvidia-nvfp4-dflash-2x-dgx-sparks Public

   GLM-5.3-Flash NVIDIA official NVFP4 + DFlash2 on 2x DGX Spark — TP=2 over RoCE, cudagraphs + async scheduling, verified 700K ctx (hardmode 94/100), one .env

   Shell 12 3

3. glm-5.3-flash-nvfp4-2x-dgx-sparks glm-5.3-flash-nvfp4-2x-dgx-sparks Public

   GLM-5.3-Flash NVFP4 (lab quant) on 2x DGX Spark — TP=2 over RoCE, one .env, compose head/worker, download/start/stop/status/tail-log

   Shell 10 2

4. EngineMetrics EngineMetrics Public

   Real-time vLLM + TensorFold performance dashboard TUI — single file, zero dependencies

   Python 9 1

5. MediaLLMProxy MediaLLMProxy Public

   OpenAI-compatible local media bridge and model-scoped reasoning/structured-output compatibility proxy.

   C# 7 1

6. qwen3.8-flash-next-2x-dgx-sparks qwen3.8-flash-next-2x-dgx-sparks Public

   Generalized Qwen3.8-Flash-Next FP8 TP2 serving stack for 2x DGX Spark (RoCE) — one .env, compose head/worker, start/stop/status/download

   Shell 7 1